© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 13205
    Prev
    Next
    INDEX
    Explanations

    sequences that suggest continuation or progression

    oai_token-act-pair · gpt-3.5-turbo

    repetitive patterns and phrases indicating continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogun
    -0.72
    obyl
    -0.71
    enna
    -0.69
    orthy
    -0.67
    urus
    -0.63
    qualified
    -0.63
    eatured
    -0.62
    ibaba
    -0.62
    ected
    -0.62
    ortium
    -0.61
    POSITIVE LOGITS
     until
    1.37
     till
    1.32
     endlessly
    1.21
    until
    1.14
     alternating
    1.03
     repeating
    1.00
     Eventually
    0.96
     increments
    0.95
     repeats
    0.95
     repet
    0.94
    Activations Density 0.543%

    No Known Activations